Examining a structure formed on a semiconductor wafer using machine learning systems

Abstract

A structure formed on a semiconductor wafer is examined by obtaining a first diffraction signal measured from the structure using an optical metrology device. A first profile is obtained from a first machine learning system using the first diffraction signal obtained as an input to the first machine learning system. The first machine learning system is configured to generate a profile as an output for a diffraction signal received as an input. A second profile is obtained from a second machine learning system using the first profile obtained from the first machine learning system as an input to the second machine learning system. The second machine learning system is configured to generate a diffraction signal as an output for a profile received as an input. The first and second profiles include one or more parameters that characterize one or more features of the structure.

1. A method of examining a structure formed on a semiconductor wafer, the method comprising:
 a) obtaining a first diffraction signal measured from the structure using an optical metrology device; 
 b) obtaining a first profile from a first machine learning system using the first diffraction signal obtained in a) as an input to the first machine learning system, wherein the first machine learning system is configured to generate a profile as an output for a diffraction signal received as an input; and 
 c) obtaining a second profile from a second machine learning system using the first profile obtained from the first machine learning system as an input to the second machine learning system, wherein the second machine learning system is configured to generate a diffraction signal as an output for a profile received as an input, and wherein the first and second profiles include one or more parameters that characterize one or more features of the structure. 
 
   
   
     2. The method of  claim 1 , wherein c) comprises:
 d) inputting the first profile as an input to the second machine learning system, wherein the second machine learning system outputs a second diffraction signal; 
 e) comparing the first diffraction signal to the second diffraction signal; 
 f) when the first and second diffraction signals do not match within one or more matching criteria, altering one or more parameters of the first profile; and 
 g) iterating d), e), and f) until the first and second diffraction signals match within the one or more matching criteria, wherein the one or more parameters of the first profile altered in f) are used in iterating d). 
 
   
   
     3. The method of  claim 2 , wherein, when the first and second diffraction signals match within the one or more matching criteria, the second profile is the same as the first profile used as the input to the second machine learning system to output the second diffraction signal that matched the first diffraction signal within the one or more matching criteria. 
   
   
     4. The method of  claim 2 , wherein an optimization algorithm is applied in iterating d), e), and f). 
   
   
     5. The method of  claim 4 , wherein the optimization algorithm is a Gauss-Newton, gradient descent, simulated annealing, or Levenberg-Marquardt algorithm. 
   
   
     6. The method of  claim 1 , wherein the second machine learning system was trained using a training process, the training process comprising:
 obtaining a first set of training data, the first set of training data having profile and diffraction signal pairs; and 
 using the profile and diffraction signal pairs from the first set of training data to train the second machine learning system to generate a diffraction signal as an output for a profile received as an input. 
 
   
   
     7. The method of  claim 6 , wherein the first machine learning system was trained using the training process, the training process further comprising:
 generating a second set of training data using the second machine learning system after the second machine learning system has been trained using the first set of training data, the second set of training data having diffraction signal and profile pairs; and 
 using the diffraction signal and profile pairs from the second set of training data to train the first machine learning system to generate a profile as an output for a diffraction signal received as an input. 
 
   
   
     8. The method of  claim 6 , wherein the diffraction signals in the first set of training data were generated using a modeling technique prior to training the first and second machine learning systems. 
   
   
     9. The method of  claim 8 , wherein the modeling technique includes rigorous coupled wave analysis, integral method, Fresnel method, finite analysis, or modal analysis. 
   
   
     10. The method of  claim 1 , wherein the first and second machine learning systems are neural networks. 
   
   
     11. A method of training machine learning systems to be used in examining a structure formed on a semiconductor wafer, wherein a first machine learning system is trained to output a profile for a diffraction signal received as an input, wherein a second machine learning system is trained to output a diffraction signal for a profile received as an input, and wherein the profiles include one or more parameters that characterize one or more features of the structure to be examined, the method comprising:
 a) obtaining a first set of training data, the first set of training data having profile and diffraction signal pairs; 
 b) training the second machine learning system using the first set of training data; 
 c) after the second machine learning system is trained, generating a second set of training data using the second machine learning system, the second set of training data having diffraction signal and profile pairs; and 
 d) training the first machine learning system using the second set of training data. 
 
   
   
     12. The method of  claim 11 , wherein the diffraction signals in the first set of training data were generated using a modeling technique prior to training the first and second machine learning systems. 
   
   
     13. The method of  claim 12 , wherein the modeling technique is rigorous coupled wave analysis, integral method, Fresnel method, finite analysis, or modal analysis. 
   
   
     14. A computer-readable storage medium containing computer executable instructions for causing a computer to examine a structure formed on a semiconductor wafer, comprising instructions for:
 a) obtaining a first diffraction signal measured from the structure using an optical metrology device; 
 b) obtaining a first profile from a first machine learning system using the first diffraction signal obtained in a) as an input to the first machine learning system, wherein the first machine learning system is configured to generate a profile as an output for a diffraction signal received as an input; and 
 c) obtaining a second profile from a second machine learning system using the first profile obtained from the first machine learning system as an input to the second machine learning system, wherein the second machine learning system is configured to generate a diffraction signal as an output for a profile received as an input, and wherein the first and second profiles include one or more parameters that characterize one or more features of the structure. 
 
   
   
     15. The computer-readable storage medium of  claim 14 , wherein c) comprises:
 d) inputting the first profile as an input to the second machine learning system, wherein the second machine learning system outputs a second diffraction signal; 
 e) comparing the first diffraction signal to the second diffraction signal; 
 f) when the first and second diffraction signals do not match within one or more matching criteria, altering one or more parameters of the first profile; and 
 g) iterating d), e), and f) until the first and second diffraction signals match within the one or more matching criteria, wherein the one or more parameters of the first profile altered in f) is used in iterating d). 
 
   
   
     16. The computer-readable storage medium of  claim 15 , wherein, when the first and second diffraction signals match within the one or more matching criteria, the second profile is the same as the first profile used as the input to the second machine learning system to output the second diffraction signal that matched the first diffraction signal within the one or more matching criteria. 
   
   
     17. The computer-readable storage medium of  claim 15 , wherein an optimization algorithm is applied in iterating d), e), and f). 
   
   
     18. A system to examine a structure formed on a semiconductor wafer, the system comprising:
 a first machine learning system configured to receive a first diffraction signal and generate a profile as an output, wherein the profile includes one or more parameters that characterize one or more features of the structure; and 
 a second machine learning system configured to receive the profile generated as the output from the first machine learning system and generate a second diffraction signal. 
 
   
   
     19. The system of  claim 18 , further comprising:
 a comparator configured to compare the first and second diffraction signals. 
 
   
   
     20. The system of  claim 19 , wherein, when the first and second diffraction signals do not match within one or more matching criteria, additional second diffraction signals are generated using the second machine learning system by altering one or more parameters of the profile until the first and second diffraction signals match within the one or more matching criteria. 
   
   
     21. The system of  claim 20 , further comprising:
 an optimizer configured to apply an optimization algorithm to obtain a second diffraction signal that matches the first diffraction signal within the one or more matching criteria. 
 
   
   
     22. The system of  claim 18 , further comprising:
 an optical metrology device configured to measure a diffraction signal from the structure, wherein the first diffraction signal received by the first machine learning system is measured using the optical metrology device. 
 
   
   
     23. The system of  claim 22 , wherein the optical metrology device is an ellipsometer or a reflectometer. 
   
   
     24. The system of  claim 18 , wherein the first and second machine learning systems are neural networks.